AIpacman offers a comprehensive Python toolkit for developing, visualizing, and benchmarking AI agents in the classic Pac-Man environment. It includes implementations of search algorithms (DFS, BFS, A*, UCS), adversarial techniques (Minimax, Alpha-Beta, Expectimax), and reinforcement learning methods (Q-Learning). With flexible maze configurations, performance metrics, and CLI controls, users can easily extend agents, analyze strategies, and gain hands-on AI experience.
AIpacman offers a comprehensive Python toolkit for developing, visualizing, and benchmarking AI agents in the classic Pac-Man environment. It includes implementations of search algorithms (DFS, BFS, A*, UCS), adversarial techniques (Minimax, Alpha-Beta, Expectimax), and reinforcement learning methods (Q-Learning). With flexible maze configurations, performance metrics, and CLI controls, users can easily extend agents, analyze strategies, and gain hands-on AI experience.
AIpacman is an open-source Python project that simulates the Pac-Man game environment for AI experimentation. Users can choose from built-in agents or implement custom ones using search algorithms like DFS, BFS, A*, UCS; adversarial methods such as Minimax with Alpha-Beta pruning and Expectimax; or reinforcement learning techniques like Q-Learning. The framework provides configurable mazes, performance logging, visualization of agent decision-making, and a command-line interface for running matches and comparing scores. It is designed to facilitate educational lessons, research benchmarks, and hobbyist projects in AI and game development.